{"list":"other","total":52,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"2206.15378","title":"Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning","created":"2022-06-30","cited_by_count":131},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"2102.05406","title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","created":"2021-02-10","cited_by_count":98},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"2001.02811","title":"Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors","created":"2020-01-09","cited_by_count":85},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","cited_by_count":60},{"id":"2106.13687","title":"panda-gym: Open-source goal-conditioned environments for robotic learning","created":"2021-06-25","cited_by_count":59},{"id":"1909.12906","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","created":"2019-09-16","cited_by_count":49},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41},{"id":"1906.07073","title":"Is the Policy Gradient a Gradient?","created":"2019-06-17","cited_by_count":40},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40},{"id":"1811.09013","title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","created":"2018-11-22","cited_by_count":34},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33},{"id":"1906.01624","title":"Off-Policy Evaluation via Off-Policy Classification","created":"2019-06-04","cited_by_count":32},{"id":"2007.05078","title":"A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces","created":"2020-07-09","cited_by_count":32},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29},{"id":"2106.09119","title":"Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL","created":"2021-06-16","cited_by_count":24},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17},{"id":"2110.12997","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","created":"2021-10-25","cited_by_count":15},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15},{"id":"2210.08349","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","created":"2022-10-15","cited_by_count":14},{"id":"2007.02879","title":"Fast Adaptation via Policy-Dynamics Value Functions","created":"2020-07-06","cited_by_count":13},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8}],"next_cursor":null}